Data scientist lead

LEAD DATA SCIENTIST

Security Knowledge Graphs & Cyber AI

Role Level

Lead

Experience

10+ years overall; 5+ years in AI/ML or graph analytics

Location

Flexible / Hybrid

Employment Type

Full-time

Role Purpose

Lead the design, engineering, and operationalization of enterprise Security Knowledge Graphs that connect security telemetry, assets, identities, vulnerabilities, threats, controls, and incidents into a trusted intelligence layer. The role is highly hands-on and combines data science, graph engineering, cybersecurity analytics, semantic modeling, and technical leadership to enable attack-path analysis, threat investigation, exposure prioritization, GraphRAG, and AI-assisted security operations.

Key Responsibilities

• Design the Security Knowledge Graph architecture, ontology, taxonomy, entity model, relationship model, provenance model, and lifecycle standards.

• Build production-grade graph ingestion and transformation pipelines for SIEM, EDR/XDR, IAM/PAM, CMDB, vulnerability scanners, cloud security platforms, threat intelligence feeds, security data lakes, and case-management systems.

• Develop entity extraction, identity resolution, deduplication, schema mapping, relationship inference, confidence scoring, temporal modeling, and graph enrichment capabilities.

• Model assets, applications, users, service accounts, privileges, vulnerabilities, misconfigurations, controls, alerts, incidents, indicators, threat actors, campaigns, tactics, techniques, and procedures.

• Implement graph analytics for attack paths, blast radius, privilege escalation, lateral movement, toxic combinations, identity exposure, control gaps, and vulnerability prioritization.

• Build and evaluate graph algorithms and ML models including centrality, community detection, similarity, anomaly detection, node classification, link prediction, embeddings, and Graph Neural Networks.

• Design GraphRAG and knowledge-grounded security assistants that combine graph traversal, vector retrieval, structured evidence, LLM reasoning, citations, and human approval controls.

• Partner with SOC, threat intelligence, IAM, vulnerability management, cloud security, architecture, data engineering, and product teams to convert operational problems into reusable graph-powered capabilities.

• Own technical design reviews, coding standards, model validation, observability, performance tuning, security controls, documentation, and production-readiness gates.

• Mentor data scientists and engineers while remaining accountable for prototypes, reference implementations, critical code, troubleshooting, and complex customer or stakeholder demonstrations.

Mandatory Hands-on Technical Skills

• Knowledge graphs: Ontology and semantic model design; property graphs and RDF; graph schema evolution; knowledge representation; provenance; graph quality; entity and relationship resolution.

• Graph platforms: Deep implementation experience with Neo4j and Cypher; working knowledge of at least one additional platform such as Amazon Neptune, TigerGraph, Azure Cosmos DB Gremlin, ArangoDB, or JanusGraph.

• Graph data science: Neo4j Graph Data Science, NetworkX, PyTorch Geometric or DGL; graph embeddings, pathfinding, similarity, clustering, link prediction, node classification, anomaly detection, and GNN development.

• Programming and engineering: Advanced Python and SQL; APIs; test automation; data structures; distributed processing; Git; CI/CD; containers; infrastructure awareness; production debugging and performance optimization.

• Data engineering: Spark or Databricks, Kafka or equivalent streaming, ETL/ELT, batch and real-time pipelines, data contracts, lineage, cataloguing, quality rules, and scalable cloud storage.

• Cybersecurity: SOC workflows, threat hunting, incident response, detection engineering, vulnerability and exposure management, IAM/PAM, Zero Trust, cloud security, and security control mapping.

• Security standards: Practical use of MITRE ATT&CK, STIX/TAXII, CVE, CWE, CAPEC, NIST frameworks, CIS Controls, and common threat-intelligence vocabularies.

• GenAI and GraphRAG: LLM-based extraction, retrieval orchestration, agent/tool integration, prompt design, evaluation, grounding, guardrails, explainability, and evidence traceability.

• MLOps and observability: Experiment tracking, model versioning, deployment, monitoring, drift and quality checks, auditability, access controls, secrets management, and cost/performance management.

Security Knowledge Graph Engineering Expectations

• Create canonical entity and relationship definitions with stable identifiers, temporal context, source lineage, evidence attributes, confidence scores, and access-control classifications.

• Develop reusable connectors and parsers for structured, semi-structured, and unstructured security sour